© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 7899
    Prev
    Next
    INDEX
    Explanations

    two-year-old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enberg
    -0.09
    elsing
    -0.09
    大å¢ŀ
    -0.08
    enhagen
    -0.08
    APER
    -0.08
    ometown
    -0.08
    иÑĢо
    -0.08
    anto
    -0.08
    enza
    -0.08
    enburg
    -0.08
    POSITIVE LOGITS
    nd
    0.13
    -thirds
    0.12
    åĴĮä¸ī
    0.10
    gether
    0.07
     mÆ°Æ¡i
    0.07
    åĬłæĭ¿å¤§
    0.07
     Hälfte
    0.07
    nde
    0.07
    ãģ£ãģįãĤĬ
    0.07
    ÅŁik
    0.06
    Activations Density 0.493%

    No Known Activations